Merge tag 'trace-v4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "New features for this release:

   - Pretty much a full rewrite of the processing of function plugins.
     i.e. echo do_IRQ:stacktrace > set_ftrace_filter

   - The rewrite was needed to add plugins to be unique to tracing
     instances. i.e. mkdir instance/foo; cd instances/foo; echo
     do_IRQ:stacktrace > set_ftrace_filter The old way was written very
     hacky. This removes a lot of those hacks.

   - New "function-fork" tracing option. When set, pids in the
     set_ftrace_pid will have their children added when the processes
     with their pids listed in the set_ftrace_pid file forks.

   - Exposure of "maxactive" for kretprobe in kprobe_events

   - Allow for builtin init functions to be traced by the function
     tracer (via the kernel command line). Module init function tracing
     will come in the next release.

   - Added more selftests, and have selftests also test in an instance"

* tag 'trace-v4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (60 commits)
  ring-buffer: Return reader page back into existing ring buffer
  selftests: ftrace: Allow some event trigger tests to run in an instance
  selftests: ftrace: Have some basic tests run in a tracing instance too
  selftests: ftrace: Have event tests also run in an tracing instance
  selftests: ftrace: Make func_event_triggers and func_traceonoff_triggers tests do instances
  selftests: ftrace: Allow some tests to be run in a tracing instance
  tracing/ftrace: Allow for instances to trigger their own stacktrace probes
  tracing/ftrace: Allow for the traceonoff probe be unique to instances
  tracing/ftrace: Enable snapshot function trigger to work with instances
  tracing/ftrace: Allow instances to have their own function probes
  tracing/ftrace: Add a better way to pass data via the probe functions
  ftrace: Dynamically create the probe ftrace_ops for the trace_array
  tracing: Pass the trace_array into ftrace_probe_ops functions
  tracing: Have the trace_array hold the list of registered func probes
  ftrace: If the hash for a probe fails to update then free what was initialized
  ftrace: Have the function probes call their own function
  ftrace: Have each function probe use its own ftrace_ops
  ftrace: Have unregister_ftrace_function_probe_func() return a value
  ftrace: Add helper function ftrace_hash_move_and_update_ops()
  ftrace: Remove data field from ftrace_func_probe structure
  ...

40 files changed, 1902 insertions, 656 deletions

diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index 5ea85059db3b..1a3a3d6bc2a8 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -24,7 +24,7 @@ current_tracer. Instead of that, add probe points via
 Synopsis of kprobe_events
 -------------------------
   p[:[GRP/]EVENT] [MOD:]SYM[+offs]|MEMADDR [FETCHARGS]	: Set a probe
-  r[:[GRP/]EVENT] [MOD:]SYM[+0] [FETCHARGS]		: Set a return probe
+  r[MAXACTIVE][:[GRP/]EVENT] [MOD:]SYM[+0] [FETCHARGS]	: Set a return probe
   -:[GRP/]EVENT						: Clear a probe
 
  GRP		: Group name. If omitted, use "kprobes" for it.
@@ -33,6 +33,9 @@ Synopsis of kprobe_events
  MOD		: Module name which has given SYM.
  SYM[+offs]	: Symbol+offset where the probe is inserted.
  MEMADDR	: Address where the probe is inserted.
+ MAXACTIVE	: Maximum number of instances of the specified function that
+		  can be probed simultaneously, or 0 for the default value
+		  as defined in Documentation/kprobes.txt section 1.3.1.
 
  FETCHARGS	: Arguments. Each probe can have up to 128 args.
   %REG		: Fetch register REG
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 5b7153540727..8ee76dce9140 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -533,7 +533,13 @@ static void do_sync_core(void *data)
 
 static void run_sync(void)
 {
-	int enable_irqs = irqs_disabled();
+	int enable_irqs;
+
+	/* No need to sync if there's only one CPU */
+	if (num_online_cpus() == 1)
+		return;
+
+	enable_irqs = irqs_disabled();
 
 	/* We may be called with interrupts disabled (on bootup). */
 	if (enable_irqs)
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 3633e8beff39..6d2a63e4ea52 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -42,8 +42,10 @@
 /* Main tracing buffer and events set up */
 #ifdef CONFIG_TRACING
 void trace_init(void);
+void early_trace_init(void);
 #else
 static inline void trace_init(void) { }
+static inline void early_trace_init(void) { }
 #endif
 
 struct module;
@@ -144,6 +146,10 @@ struct ftrace_ops_hash {
 	struct ftrace_hash		*filter_hash;
 	struct mutex			regex_lock;
 };
+
+void ftrace_free_init_mem(void);
+#else
+static inline void ftrace_free_init_mem(void) { }
 #endif
 
 /*
@@ -260,6 +266,7 @@ static inline int ftrace_nr_registered_ops(void)
 }
 static inline void clear_ftrace_function(void) { }
 static inline void ftrace_kill(void) { }
+static inline void ftrace_free_init_mem(void) { }
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_STACK_TRACER
@@ -279,15 +286,45 @@ int
 stack_trace_sysctl(struct ctl_table *table, int write,
 		   void __user *buffer, size_t *lenp,
 		   loff_t *ppos);
-#endif
 
-struct ftrace_func_command {
-	struct list_head	list;
-	char			*name;
-	int			(*func)(struct ftrace_hash *hash,
-					char *func, char *cmd,
-					char *params, int enable);
-};
+/* DO NOT MODIFY THIS VARIABLE DIRECTLY! */
+DECLARE_PER_CPU(int, disable_stack_tracer);
+
+/**
+ * stack_tracer_disable - temporarily disable the stack tracer
+ *
+ * There's a few locations (namely in RCU) where stack tracing
+ * cannot be executed. This function is used to disable stack
+ * tracing during those critical sections.
+ *
+ * This function must be called with preemption or interrupts
+ * disabled and stack_tracer_enable() must be called shortly after
+ * while preemption or interrupts are still disabled.
+ */
+static inline void stack_tracer_disable(void)
+{
+	/* Preemption or interupts must be disabled */
+	if (IS_ENABLED(CONFIG_PREEMPT_DEBUG))
+		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
+	this_cpu_inc(disable_stack_tracer);
+}
+
+/**
+ * stack_tracer_enable - re-enable the stack tracer
+ *
+ * After stack_tracer_disable() is called, stack_tracer_enable()
+ * must be called shortly afterward.
+ */
+static inline void stack_tracer_enable(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_DEBUG))
+		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
+	this_cpu_dec(disable_stack_tracer);
+}
+#else
+static inline void stack_tracer_disable(void) { }
+static inline void stack_tracer_enable(void) { }
+#endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
@@ -315,30 +352,6 @@ void ftrace_bug(int err, struct dyn_ftrace *rec);
 
 struct seq_file;
 
-struct ftrace_probe_ops {
-	void			(*func)(unsigned long ip,
-					unsigned long parent_ip,
-					void **data);
-	int			(*init)(struct ftrace_probe_ops *ops,
-					unsigned long ip, void **data);
-	void			(*free)(struct ftrace_probe_ops *ops,
-					unsigned long ip, void **data);
-	int			(*print)(struct seq_file *m,
-					 unsigned long ip,
-					 struct ftrace_probe_ops *ops,
-					 void *data);
-};
-
-extern int
-register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
-			      void *data);
-extern void
-unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
-				void *data);
-extern void
-unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops);
-extern void unregister_ftrace_function_probe_all(char *glob);
-
 extern int ftrace_text_reserved(const void *start, const void *end);
 
 extern int ftrace_nr_registered_ops(void);
@@ -400,9 +413,6 @@ void ftrace_set_global_notrace(unsigned char *buf, int len, int reset);
 void ftrace_free_filter(struct ftrace_ops *ops);
 void ftrace_ops_set_global_filter(struct ftrace_ops *ops);
 
-int register_ftrace_command(struct ftrace_func_command *cmd);
-int unregister_ftrace_command(struct ftrace_func_command *cmd);
-
 enum {
 	FTRACE_UPDATE_CALLS		= (1 << 0),
 	FTRACE_DISABLE_CALLS		= (1 << 1),
@@ -433,8 +443,8 @@ enum {
 	FTRACE_ITER_FILTER	= (1 << 0),
 	FTRACE_ITER_NOTRACE	= (1 << 1),
 	FTRACE_ITER_PRINTALL	= (1 << 2),
-	FTRACE_ITER_DO_HASH	= (1 << 3),
-	FTRACE_ITER_HASH	= (1 << 4),
+	FTRACE_ITER_DO_PROBES	= (1 << 3),
+	FTRACE_ITER_PROBE	= (1 << 4),
 	FTRACE_ITER_ENABLED	= (1 << 5),
 };
 
@@ -618,14 +628,6 @@ static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_module_init(struct module *mod) { }
 static inline void ftrace_module_enable(struct module *mod) { }
 static inline void ftrace_release_mod(struct module *mod) { }
-static inline __init int register_ftrace_command(struct ftrace_func_command *cmd)
-{
-	return -EINVAL;
-}
-static inline __init int unregister_ftrace_command(char *cmd_name)
-{
-	return -EINVAL;
-}
 static inline int ftrace_text_reserved(const void *start, const void *end)
 {
 	return 0;
diff --git a/include/linux/init.h b/include/linux/init.h
index 79af0962fd52..94769d687cf0 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -39,7 +39,7 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(.init.text) __cold notrace __latent_entropy
+#define __init		__section(.init.text) __cold __inittrace __latent_entropy
 #define __initdata	__section(.init.data)
 #define __initconst	__section(.init.rodata)
 #define __exitdata	__section(.exit.data)
@@ -68,8 +68,10 @@
 
 #ifdef MODULE
 #define __exitused
+#define __inittrace notrace
 #else
 #define __exitused  __used
+#define __inittrace
 #endif
 
 #define __exit          __section(.exit.text) __exitused __cold notrace
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index de88b33c0974..dea8f17b2fe3 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -97,6 +97,7 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 			       unsigned long secs,
 			       unsigned long c_old,
 			       unsigned long c);
+bool rcu_irq_enter_disabled(void);
 #else
 static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
 					  int *flags,
@@ -113,6 +114,10 @@ static inline void rcutorture_record_test_transition(void)
 static inline void rcutorture_record_progress(unsigned long vernum)
 {
 }
+static inline bool rcu_irq_enter_disabled(void)
+{
+	return false;
+}
 #ifdef CONFIG_RCU_TRACE
 void do_trace_rcu_torture_read(const char *rcutorturename,
 			       struct rcu_head *rhp,
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index b6d4568795a7..ee9b461af095 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -185,7 +185,7 @@ size_t ring_buffer_page_len(void *page);
 
 
 void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu);
-void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data);
+void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data);
 int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page,
 			  size_t len, int cpu, int full);
 
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 0af63c4381b9..a556805eff8a 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -138,16 +138,7 @@ enum print_line_t {
 	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
 };
 
-/*
- * Several functions return TRACE_TYPE_PARTIAL_LINE if the trace_seq
- * overflowed, and TRACE_TYPE_HANDLED otherwise. This helper function
- * simplifies those functions and keeps them in sync.
- */
-static inline enum print_line_t trace_handle_return(struct trace_seq *s)
-{
-	return trace_seq_has_overflowed(s) ?
-		TRACE_TYPE_PARTIAL_LINE : TRACE_TYPE_HANDLED;
-}
+enum print_line_t trace_handle_return(struct trace_seq *s);
 
 void tracing_generic_entry_update(struct trace_entry *entry,
 				  unsigned long flags,
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index f72fcfe0e66a..cc48cb2ce209 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -128,7 +128,7 @@ extern void syscall_unregfunc(void);
  * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just
  * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto".
  */
-#define __DO_TRACE(tp, proto, args, cond, prercu, postrcu)		\
+#define __DO_TRACE(tp, proto, args, cond, rcucheck)			\
 	do {								\
 		struct tracepoint_func *it_func_ptr;			\
 		void *it_func;						\
@@ -136,7 +136,11 @@ extern void syscall_unregfunc(void);
 									\
 		if (!(cond))						\
 			return;						\
-		prercu;							\
+		if (rcucheck) {						\
+			if (WARN_ON_ONCE(rcu_irq_enter_disabled()))	\
+				return;					\
+			rcu_irq_enter_irqson();				\
+		}							\
 		rcu_read_lock_sched_notrace();				\
 		it_func_ptr = rcu_dereference_sched((tp)->funcs);	\
 		if (it_func_ptr) {					\
@@ -147,20 +151,19 @@ extern void syscall_unregfunc(void);
 			} while ((++it_func_ptr)->func);		\
 		}							\
 		rcu_read_unlock_sched_notrace();			\
-		postrcu;						\
+		if (rcucheck)						\
+			rcu_irq_exit_irqson();				\
 	} while (0)
 
 #ifndef MODULE
-#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args)	\
+#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) \
 	static inline void trace_##name##_rcuidle(proto)		\
 	{								\
 		if (static_key_false(&__tracepoint_##name.key))		\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
-				TP_CONDITION(cond),			\
-				rcu_irq_enter_irqson(),			\
-				rcu_irq_exit_irqson());			\
+				TP_CONDITION(cond), 1);			\
 	}
 #else
 #define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args)
@@ -186,7 +189,7 @@ extern void syscall_unregfunc(void);
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
-				TP_CONDITION(cond),,);			\
+				TP_CONDITION(cond), 0);			\
 		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
 			rcu_read_lock_sched_notrace();			\
 			rcu_dereference_sched(__tracepoint_##name.funcs);\
diff --git a/init/main.c b/init/main.c
index b1b9dbf7622f..cc48053bb39f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -545,6 +545,11 @@ asmlinkage __visible void __init start_kernel(void)
 	trap_init();
 	mm_init();
 
+	ftrace_init();
+
+	/* trace_printk can be enabled here */
+	early_trace_init();
+
 	/*
 	 * Set up the scheduler prior starting any interrupts (such as the
 	 * timer interrupt). Full topology setup happens at smp_init()
@@ -570,7 +575,7 @@ asmlinkage __visible void __init start_kernel(void)
 
 	rcu_init();
 
-	/* trace_printk() and trace points may be used after this */
+	/* Trace events are available after this */
 	trace_init();
 
 	context_tracking_init();
@@ -670,8 +675,6 @@ asmlinkage __visible void __init start_kernel(void)
 		efi_free_boot_services();
 	}
 
-	ftrace_init();
-
 	/* Do the rest non-__init'ed, we're now alive */
 	rest_init();
 }
@@ -959,6 +962,7 @@ static int __ref kernel_init(void *unused)
 	kernel_init_freeable();
 	/* need to finish all async __init code before freeing the memory */
 	async_synchronize_full();
+	ftrace_free_init_mem();
 	free_initmem();
 	mark_readonly();
 	system_state = SYSTEM_RUNNING;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 50fee7689e71..a6dcf3bd244f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -57,6 +57,7 @@
 #include <linux/random.h>
 #include <linux/trace_events.h>
 #include <linux/suspend.h>
+#include <linux/ftrace.h>
 
 #include "tree.h"
 #include "rcu.h"
@@ -284,6 +285,20 @@ static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 };
 
 /*
+ * There's a few places, currently just in the tracing infrastructure,
+ * that uses rcu_irq_enter() to make sure RCU is watching. But there's
+ * a small location where that will not even work. In those cases
+ * rcu_irq_enter_disabled() needs to be checked to make sure rcu_irq_enter()
+ * can be called.
+ */
+static DEFINE_PER_CPU(bool, disable_rcu_irq_enter);
+
+bool rcu_irq_enter_disabled(void)
+{
+	return this_cpu_read(disable_rcu_irq_enter);
+}
+
+/*
  * Record entry into an extended quiescent state.  This is only to be
  * called when not already in an extended quiescent state.
  */
@@ -771,25 +786,24 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 }
 
 /*
- * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state
+ * rcu_eqs_enter_common - current CPU is entering an extended quiescent state
  *
- * If the new value of the ->dynticks_nesting counter now is zero,
- * we really have entered idle, and must do the appropriate accounting.
- * The caller must have disabled interrupts.
+ * Enter idle, doing appropriate accounting.  The caller must have
+ * disabled interrupts.
  */
-static void rcu_eqs_enter_common(long long oldval, bool user)
+static void rcu_eqs_enter_common(bool user)
 {
 	struct rcu_state *rsp;
 	struct rcu_data *rdp;
-	RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);)
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
-	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
+	trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0);
 	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 	    !user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
 			idle_task(smp_processor_id());
 
-		trace_rcu_dyntick(TPS("Error on entry: not idle task"), oldval, 0);
+		trace_rcu_dyntick(TPS("Error on entry: not idle task"), rdtp->dynticks_nesting, 0);
 		rcu_ftrace_dump(DUMP_ORIG);
 		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
 			  current->pid, current->comm,
@@ -800,7 +814,10 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
 		do_nocb_deferred_wakeup(rdp);
 	}
 	rcu_prepare_for_idle();
-	rcu_dynticks_eqs_enter();
+	__this_cpu_inc(disable_rcu_irq_enter);
+	rdtp->dynticks_nesting = 0; /* Breaks tracing momentarily. */
+	rcu_dynticks_eqs_enter(); /* After this, tracing works again. */
+	__this_cpu_dec(disable_rcu_irq_enter);
 	rcu_dynticks_task_enter();
 
 	/*
@@ -821,19 +838,15 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
  */
 static void rcu_eqs_enter(bool user)
 {
-	long long oldval;
 	struct rcu_dynticks *rdtp;
 
 	rdtp = this_cpu_ptr(&rcu_dynticks);
-	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     (oldval & DYNTICK_TASK_NEST_MASK) == 0);
-	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
-		rdtp->dynticks_nesting = 0;
-		rcu_eqs_enter_common(oldval, user);
-	} else {
+		     (rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0);
+	if ((rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
+		rcu_eqs_enter_common(user);
+	else
 		rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
-	}
 }
 
 /**
@@ -892,19 +905,18 @@ void rcu_user_enter(void)
  */
 void rcu_irq_exit(void)
 {
-	long long oldval;
 	struct rcu_dynticks *rdtp;
 
 	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
 	rdtp = this_cpu_ptr(&rcu_dynticks);
-	oldval = rdtp->dynticks_nesting;
-	rdtp->dynticks_nesting--;
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     rdtp->dynticks_nesting < 0);
-	if (rdtp->dynticks_nesting)
-		trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
-	else
-		rcu_eqs_enter_common(oldval, true);
+		     rdtp->dynticks_nesting < 1);
+	if (rdtp->dynticks_nesting <= 1) {
+		rcu_eqs_enter_common(true);
+	} else {
+		trace_rcu_dyntick(TPS("--="), rdtp->dynticks_nesting, rdtp->dynticks_nesting - 1);
+		rdtp->dynticks_nesting--;
+	}
 	rcu_sysidle_enter(1);
 }
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 9619b5768e4b..7e06f04e98fe 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -134,7 +134,8 @@ config FUNCTION_TRACER
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
-        select GLOB
+	select GLOB
+	select TASKS_RCU if PREEMPT
 	help
 	  Enable the kernel to trace every kernel function. This is done
 	  by using a compiler feature to insert a small, 5-byte No-Operation
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index dd3e91d68dc7..00077a57b746 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -36,6 +36,7 @@
 
 #include <trace/events/sched.h>
 
+#include <asm/sections.h>
 #include <asm/setup.h>
 
 #include "trace_output.h"
@@ -1095,22 +1096,20 @@ static bool update_all_ops;
 # error Dynamic ftrace depends on MCOUNT_RECORD
 #endif
 
-static struct hlist_head ftrace_func_hash[FTRACE_FUNC_HASHSIZE] __read_mostly;
-
-struct ftrace_func_probe {
-	struct hlist_node	node;
-	struct ftrace_probe_ops	*ops;
-	unsigned long		flags;
-	unsigned long		ip;
-	void			*data;
-	struct list_head	free_list;
-};
-
 struct ftrace_func_entry {
 	struct hlist_node hlist;
 	unsigned long ip;
 };
 
+struct ftrace_func_probe {
+	struct ftrace_probe_ops	*probe_ops;
+	struct ftrace_ops	ops;
+	struct trace_array	*tr;
+	struct list_head	list;
+	void			*data;
+	int			ref;
+};
+
 /*
  * We make these constant because no one should touch them,
  * but they are used as the default "empty hash", to avoid allocating
@@ -1271,7 +1270,7 @@ static void
 remove_hash_entry(struct ftrace_hash *hash,
 		  struct ftrace_func_entry *entry)
 {
-	hlist_del(&entry->hlist);
+	hlist_del_rcu(&entry->hlist);
 	hash->count--;
 }
 
@@ -2807,18 +2806,28 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	 * callers are done before leaving this function.
 	 * The same goes for freeing the per_cpu data of the per_cpu
 	 * ops.
-	 *
-	 * Again, normal synchronize_sched() is not good enough.
-	 * We need to do a hard force of sched synchronization.
-	 * This is because we use preempt_disable() to do RCU, but
-	 * the function tracers can be called where RCU is not watching
-	 * (like before user_exit()). We can not rely on the RCU
-	 * infrastructure to do the synchronization, thus we must do it
-	 * ourselves.
 	 */
 	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU)) {
+		/*
+		 * We need to do a hard force of sched synchronization.
+		 * This is because we use preempt_disable() to do RCU, but
+		 * the function tracers can be called where RCU is not watching
+		 * (like before user_exit()). We can not rely on the RCU
+		 * infrastructure to do the synchronization, thus we must do it
+		 * ourselves.
+		 */
 		schedule_on_each_cpu(ftrace_sync);
 
+		/*
+		 * When the kernel is preeptive, tasks can be preempted
+		 * while on a ftrace trampoline. Just scheduling a task on
+		 * a CPU is not good enough to flush them. Calling
+		 * synchornize_rcu_tasks() will wait for those tasks to
+		 * execute and either schedule voluntarily or enter user space.
+		 */
+		if (IS_ENABLED(CONFIG_PREEMPT))
+			synchronize_rcu_tasks();
+
 		arch_ftrace_trampoline_free(ops);
 
 		if (ops->flags & FTRACE_OPS_FL_PER_CPU)
@@ -3055,34 +3064,63 @@ struct ftrace_iterator {
 	struct ftrace_page		*pg;
 	struct dyn_ftrace		*func;
 	struct ftrace_func_probe	*probe;
+	struct ftrace_func_entry	*probe_entry;
 	struct trace_parser		parser;
 	struct ftrace_hash		*hash;
 	struct ftrace_ops		*ops;
-	int				hidx;
+	int				pidx;
 	int				idx;
 	unsigned			flags;
 };
 
 static void *
-t_hash_next(struct seq_file *m, loff_t *pos)
+t_probe_next(struct seq_file *m, loff_t *pos)
 {
 	struct ftrace_iterator *iter = m->private;
+	struct trace_array *tr = iter->ops->private;
+	struct list_head *func_probes;
+	struct ftrace_hash *hash;
+	struct list_head *next;
 	struct hlist_node *hnd = NULL;
 	struct hlist_head *hhd;
+	int size;
 
 	(*pos)++;
 	iter->pos = *pos;
 
-	if (iter->probe)
-		hnd = &iter->probe->node;
- retry:
-	if (iter->hidx >= FTRACE_FUNC_HASHSIZE)
+	if (!tr)
 		return NULL;
 
-	hhd = &ftrace_func_hash[iter->hidx];
+	func_probes = &tr->func_probes;
+	if (list_empty(func_probes))
+		return NULL;
+
+	if (!iter->probe) {
+		next = func_probes->next;
+		iter->probe = list_entry(next, struct ftrace_func_probe, list);
+	}
+
+	if (iter->probe_entry)
+		hnd = &iter->probe_entry->hlist;
+
+	hash = iter->probe->ops.func_hash->filter_hash;
+	size = 1 << hash->size_bits;
+
+ retry:
+	if (iter->pidx >= size) {
+		if (iter->probe->list.next == func_probes)
+			return NULL;
+		next = iter->probe->list.next;
+		iter->probe = list_entry(next, struct ftrace_func_probe, list);
+		hash = iter->probe->ops.func_hash->filter_hash;
+		size = 1 << hash->size_bits;
+		iter->pidx = 0;
+	}
+
+	hhd = &hash->buckets[iter->pidx];
 
 	if (hlist_empty(hhd)) {
-		iter->hidx++;
+		iter->pidx++;
 		hnd = NULL;
 		goto retry;
 	}
@@ -3092,7 +3130,7 @@ t_hash_next(struct seq_file *m, loff_t *pos)
 	else {
 		hnd = hnd->next;
 		if (!hnd) {
-			iter->hidx++;
+			iter->pidx++;
 			goto retry;
 		}
 	}
@@ -3100,26 +3138,28 @@ t_hash_next(struct seq_file *m, loff_t *pos)
 	if (WARN_ON_ONCE(!hnd))